mlsanityData to 14 Oct 2026

Perception Test 2026: Challenge Summary and Extension to City-scale Audio-Visual Reasoning

arXiv 2610.12081 ↗First posted 8 Oct 2026cs.CV cs.LGcited by 0

On the map: LLM reasoning → Spatial and embodied reasoning also fits: Multimodal reasoning

Abstract (arXiv)

Continuing the Perception Test challenge series, we organised the fourth edition as a workshop at the European Conference on Computer Vision (ECCV) 2026 in Malm"o, Sweden. This edition focused on spatial intelligence and featured four different tracks: unified multiple-choice videoQA and grounded videoQA from the original Perception Test benchmark, alongside two new tracks based on city-scale walking-tour videos (KilometerAudio and KilometerVision). In this report, we describe the new benchmarks used for the city-scale tracks and summarise the winning solutions across all tracks, including a generalist model that competed across all tracks with satisfactory performance. The winning solutions in the newly added city-scale tracks demonstrated that complex spatial and multimodal reasoning can be solved by expensive agentic pipelines, but remains difficult for multimodal models used standalone.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 4 of its 18 references that are in the map. First posted on arXiv 8 Oct 2026.

Builds on

4 of 18 references.

References · 4

  1. 2025SAM 3: Segment Anything with Conceptscited by 906
  2. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 819
  3. 2024Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmarkcited by 5
  4. 2026Perception Test 2025: Challenge Summary and a Unified VQA Extensioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Perception Test: A Diagnostic Benchmark for Multimodal Video Models
  2. 2026PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
  3. 2026SAVU-BENCH: A Real-World Benchmark for Spatial Audio-Visual Understanding
  4. 2025UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces
  5. 2025MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence
  6. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
  7. 2026CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments
  8. 2025SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing